schemagen: deduplicate enum constants that collide after sanitization
CI / build (-DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++, clang-arm64, ubuntu-latest-arm64, true) (pull_request) Successful in 51s
CI / build (-DCMAKE_C_COMPILER=gcc -DCMAKE_CXX_COMPILER=g++, gcc-arm64, ubuntu-latest-arm64, false) (pull_request) Successful in 51s
CI / pre-commit (pull_request) Successful in 51s
CI / build (-DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++, clang-amd64, ubuntu-latest-amd64, true) (pull_request) Successful in 1m29s
CI / build (-DCMAKE_C_COMPILER=gcc -DCMAKE_CXX_COMPILER=g++, gcc-amd64, ubuntu-latest-amd64, false) (pull_request) Successful in 1m22s

Distinct JSON enum values can sanitize to the same C++ identifier
(e.g. "foo-bar" and "foo_bar" both become `foo_bar`), producing an
invalid `enum class` with duplicate constants.

Add `unique_enum_identifiers()` which appends a numeric suffix to
later collisions while preserving enum declaration order, so the
index-to-JSON-value mapping used by the generated parser stays intact.

Also add contrib/schemagen/test_schemagen.py and wire the schemagen
Python tests plus the existing example.schema.json/test_gen.cpp example
into ctest via CMakeLists.txt.

Closes #4
This commit is contained in:
2026-06-18 11:02:47 -04:00
parent 7a8e5f84f2
commit 359f4f4bb6
3 changed files with 114 additions and 1 deletions
+53
View File
@@ -0,0 +1,53 @@
#!/usr/bin/env python3
"""Tests for weaseljson_schemagen.py."""
import json
import os
import subprocess
import sys
import tempfile
import unittest
SCRIPT = os.path.join(os.path.dirname(__file__), "weaseljson_schemagen.py")
class SchemagenEnumTest(unittest.TestCase):
def run_schemagen(self, schema, args=None):
"""Run schemagen on a schema dict. Returns (returncode, stdout, stderr)."""
with tempfile.NamedTemporaryFile("w", suffix=".json", delete=False) as fp:
json.dump(schema, fp)
schema_path = fp.name
try:
cmd = [sys.executable, SCRIPT, schema_path]
if args:
cmd.extend(args)
result = subprocess.run(cmd, capture_output=True, text=True, check=False)
return result.returncode, result.stdout, result.stderr
finally:
os.unlink(schema_path)
def test_colliding_enum_values_deduplicate(self):
schema = {
"type": "object",
"properties": {"role": {"enum": ["foo-bar", "foo_bar"]}},
}
rc, stdout, stderr = self.run_schemagen(schema)
self.assertEqual(rc, 0, msg=stderr)
self.assertIn("enum class Role : int { foo_bar, foo_bar_1 };", stdout)
self.assertIn(
'static constexpr const char *Role_names[] = { "foo-bar", "foo_bar" };',
stdout,
)
def test_distinct_enum_values_generate(self):
schema = {
"type": "object",
"properties": {"role": {"enum": ["admin", "user", "guest"]}},
}
rc, stdout, stderr = self.run_schemagen(schema)
self.assertEqual(rc, 0, msg=stderr)
self.assertIn("enum class Role : int { admin, user, guest };", stdout)
if __name__ == "__main__":
unittest.main()